Browse All Artificial Intelligence Content (840)

Microsoft Developer introduces Toolboxes in Microsoft Foundry as a way to make MCP (Model Context Protocol) integrations more enterprise-ready, with centralized governance, consistent authentication, and reusable configuration across multiple agents and tools.

Microsoft Developer discusses the MCP Triggers & Events experimental extension, showing how agents can poll MCP servers for events and be triggered via webhooks, and what new event-driven agent architectures this enables.

Caitie McCaffrey reviews the current state of the Model Context Protocol (MCP), focusing on the major changes in the 2026-07-28 specification release and what they mean for developers building AI agents and agent-to-agent communication patterns.

Microsoft Developer explains why Dynamic Client Registration becomes a scaling problem for MCP clients, and how switching to Client ID Metadata Documents turns the client_id into a durable, URL-based identity that servers can fetch on demand.

Jeremiah Lowin shows how MCP Apps can render interactive UI (buttons, charts, forms) directly inside AI clients, and walks through building these experiences in Python using FastMCP and Prefab—from basic components to dynamically generated interfaces.

Den Delimarsky explains how MCP authorization evolved, covering the original OAuth profile, protected resource metadata, changes to client registration, and how enterprise-managed authorization fits into the model.

Microsoft Developer demonstrates how to build modern Model Context Protocol (MCP) servers in VS Code, moving beyond simple local tool calls to more production-ready agent integrations with notifications, elicitation, stateless HTTP, and plugin-based distribution.

Sam Morrow discusses GitHub’s Model Context Protocol (MCP), covering what his team is shipping across MCP server and client implementations, plus the spec areas he’s most excited about and what’s coming next.

Jakub Oleksy’s August 2026 GitHub availability report breaks down five production incidents across GitHub Actions, authentication, and Copilot services, including what failed, how GitHub mitigated impact, and what reliability work is planned next (capacity, autoscaling, retries, and regional failover).

Authorised Territory demonstrates how to build domain-specific AI agent evaluators in .NET using Microsoft Agent Framework connected to a local Ollama model, then run automated checks against the agent’s responses to validate both content and output structure.

Nick Brady rounds up July and August 2026 updates for Microsoft Foundry, including GA for Hosted Agents, Voice Live integration, and Toolboxes, plus Model Router pool/region changes and new model releases. It also calls out SDK migrations (Python/JS/Java/.NET) and runtime requirement bumps you should test before upgrading.

willchap describes a practical framework for evaluating scientific AI systems—execution, optimization, and exploration—using three RF engineering design challenges. The post shows how Microsoft Discovery orchestrates agentic workflows that combine analytical reasoning with HFSS simulations, while surfacing assumptions, trade-offs, and decision points for human guidance.

Allison announces generally available enterprise managed permissions for GitHub Copilot agent operations, letting admins centrally decide which actions are blocked, require human approval, or run without prompting across supported Copilot clients.

Microsoft Developer demonstrates how to build a no-code AI agent in the Azure AI Foundry Portal: create a Foundry project, deploy a model, connect an MCP server for a cupcake store scenario, then validate the agent using tracing, token usage metrics, and evaluations.

Marco Casalaina breaks down Foundry IQ, Fabric IQ, Work IQ, and Web IQ, explaining them as grounding capabilities that give AI agents the right context. He maps each “IQ” to the underlying data source (knowledge bases, OneLake, Microsoft 365 apps, and the public web) and what it enables.

MinseokSong walks through a reference implementation that uses Microsoft Foundry and an Azure Function to classify incoming support emails, then uses Power Automate to validate the AI recommendation against a SharePoint allow-list, require human approval, and create an Outlook draft (without sending).

christinchen announces the general availability of Azure Copilot’s Troubleshooting Agent, a built-in experience in the Azure portal that helps teams investigate and resolve operational issues faster by combining resource context, supported diagnostics, and recommended actions—while keeping customers in control through identity and RBAC.

The Visual Studio Code Team shares the VS Code 1.138 Insiders changelog, focusing on Agent Host and Agents window improvements like shareable session links, side-by-side agent sessions, repo-first context attachment for issues/PRs, voice mode session awareness, and agent-session cleanup controls.

Allison announces agentic autofix for GitHub Code Quality, letting teams select up to 25 findings and assign them to GitHub Copilot in one action. Copilot applies fixes on a branch, validates the changes, and opens a pull request for review, with usage governed by existing enterprise policy and AI credits.

Waldek Mastykarz explains how to pick a “minimal viable model” for AI coding work by running your own evals instead of defaulting to the most expensive option. Using GitHub Copilot Chat in VS Code, he compares model quality scores and per-run costs across real upgrade scenarios to show why “smarter” can be worse value.

Allison announces updates to GitHub Copilot for JetBrains, including enterprise-managed sandbox policies, cross-file cursor jumps for next edit suggestions, global project context in chat, and enterprise policy diagnostics. The release also adds a preview integration that connects Copilot CLI terminal sessions to IDE context and improves reliability across MCP and agent sessions.

bharadwajr explains how the Azure team built GEM (Great Experiences Matter), an AI-enabled “feedback-to-fix” loop that aggregates customer feedback at scale, turns it into prioritized insights, and creates actionable Azure DevOps work items with an auditable evidence trail and human review.

Allison announces GitHub Enterprise Server (GHES) 3.22 general availability, highlighting updates for enterprise administration and collaboration, including Copilot CLI support for disconnected environments, enterprise teams, improvements to repository rulesets and required reviewers, and UI enhancements for issues and pull requests.

sbaynes announces codename MDASH, Microsoft’s multi-model agentic code-scanning system now deployed in Azure Government, aimed at finding and validating exploitable vulnerabilities across software supply chains with fewer false positives and more actionable results for security teams.

Aseem Datar explains how Microsoft Discovery applies agentic AI to scientific and engineering R&D, focusing on adaptive reasoning loops that explore multiple hypotheses, preserve evidence, and decide when to change strategy or involve domain experts. The post also highlights benchmark results for Discovery Engine with CLIO across several scientific domains.

kshatzkamer outlines a reference architecture for “orchestrated media intelligence”: an orchestration layer that connects trusted data, specialized AI models/agents, cloud infrastructure, and governance across end-to-end media workflows. The post uses Azure OpenAI, Azure AI Speech, and Azure AI Foundry examples to show how to keep humans accountable while scaling automation.

Justin Yoo walks through a practical profiling workflow for distributed .NET apps, showing how to identify which process owns a slow user interaction, use Visual Studio CPU profiling to rule out CPU-bound work, and then measure hidden async waiting that doesn’t show up in CPU samples.

GitHub explains how to make GitHub Copilot work better in a real project by giving it durable context about your repo. It covers adding custom instructions under .github, defining repeatable “skills” for tasks like testing, using custom agents for bigger workflows, and connecting MCP servers such as Playwright.

newmancheng explains how Microsoft Discovery combined agentic AI, computational predictors, and wet-lab feedback to design and validate a novel organic negolyte for redox flow batteries, with a focus on preserving negative results as durable knowledge that improves subsequent design rounds.

GitHub highlights research by Louis Abraham on how AI tools are influencing the language developers use in GitHub pull request descriptions, based on analysis of more than 460,000 PR descriptions and the rise of distinctive AI-associated terms and punctuation patterns.

Maddy Montaquila explains how a “Aspire-ified” .NET app can give a coding agent more context and control, including a single command to start containers, processes, and the debugger, plus the ability to manage resources and view logs from one place.

Andrea Griffiths and Meagan Cojocar demonstrate GitHub Copilot Cloud Agent running inside Slack and Microsoft Teams, showing how teams can create issues, review diffs, preview HTML, and analyze repository data directly from chat, plus what admins need to enable it safely in enterprise environments.

Visual Studio Code announces “MCP Live” (September 9, 9 AM PT), a live event with experts from Microsoft, GitHub, Anthropic, Okta, Prefect, and Amazon focused on updates across the Model Context Protocol (MCP) ecosystem.

John Savill recaps the major Microsoft AI updates from August 2026, including new and updated models, routing and content-understanding changes, and a set of Copilot and Azure Copilot improvements that affect how teams use AI features across developer and enterprise environments.

This week's AI roundup is about taking agentic systems from demos to production: GPT-6 Astra is now generally available in Microsoft Foundry and selectable in GitHub Copilot, while Copilot's roadmap shifts from choosing a single model to orchestrating multiple models at runtime. On the platform side, the focus is operational engineering (context control, durable memory, and observability) so agents stay predictable in cost and behavior as they run longer and use tools. Security guidance adds a reality check on egress control, attestation, and text normalization, and Copilot features like PR approvals and content exclusions raise the stakes for governance, identity, and auditability across IDE, CLI, and app workflows.

Topi Nuotos explains why his team replaced a shared Excel tracker with a Microsoft Fabric App, and how Fabric Apps adds an application layer on top of Fabric for building data-driven web apps with preconfigured infrastructure.

Authorised Territory demonstrates how to build an AI agent with the .NET Microsoft Agent Framework using a local Ollama model, then evaluate the agent locally with built-in checks to confirm response quality and that required tools were actually invoked.

GitHub explains why newer, larger AI models don’t automatically make better code reviewers, highlighting benchmark results where highly formatted, verbose reviews can still miss fundamental bugs.

John Savill runs through the Azure Weekly Update for 4th September 2026, covering a set of platform changes across compute, AKS, networking, monitoring, security, and Azure AI Foundry, with quick pointers to what’s new and where the updates land in the Azure stack.

Allison’s weekly Copilot changelog highlights new model options (Claude Fable 5.1 and Gemini 3.8 Flash), stronger content protection via honored content exclusions in Copilot app/CLI, and VS Code 1.136 updates aimed at managing agent sessions and getting pull requests ready to merge.